| Project/Area Number |
16K00428
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Web informatics, Service informatics
|
|---|
| Research Institution | Yamaguchi University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
津田 和彦 筑波大学, ビジネスサイエンス系, 教授 (50302378)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 不正検知 / 通信販売 / パターン解析 / 機械学習 |
|---|
| Outline of Final Research Achievements |
The purpose of this research is to develop novel technology to detect fraudulent transactions in the mail-order industry with the Informatics. In order to compensate for the working experiences, conventional technology, such as pattern identification was employed. In this study, analyses were performed based on the transaction recode came from a mail-order company. As a result, the weak learners have high generalization performance of detection accuracy. The results of this research can be expected to 1) improve the accuracy of credit management at the time of shipment, and 2) The risk of post-payed systems for the mail-order companies will be reduced.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究の学術的意義は，商品情報や，利用者の購買行動情報をもとにして，取引の安全度について再帰的に学習する知識生成技法であること．従来からの業務知識に基づく経験則検知や，企業独自のブラックリスト照合などにくわえて，本研究の手法を用いて不正検知件数の飛躍的向上が期待できること．その結果，受注時の与信精度向上が可能となること．にまとまられる．次に，本研究の社会的意義については，出荷判断の支援知識強化により，通信販売事業の安定的運営に貢献できることである．
|
